@untangle-code/context-artifacts 0.0.0-stage → 0.1.1

package/dist/text/line-index.d.ts

@@ -0,0 +1,61 @@
+/**
+ * Line-oriented byte indexing shared by every format adapter.
+ *
+ * Every adapter in this package chunks by *line range* (headings, top-level
+ * SQL statements, brace-delimited blocks, YAML documents, …), never by raw
+ * character offset, so a single small utility converts a 1-based inclusive
+ * line span into the byte-accurate `SourceRange` domain requires
+ * (`startLine`/`endLine` 1-based inclusive, `startByte`/`endByte` 0-based
+ * half-open — see `packages/domain/src/types/common.ts`).
+ *
+ * Splitting only ever happens right after a `\n` (0x0A, single ASCII byte,
+ * never a UTF-8 continuation byte), so every line boundary this module
+ * produces is automatically a safe UTF-8 boundary — no separate multi-byte
+ * safety check is needed the way the chunker package needs one for
+ * mid-line token-boundary splits.
+ */
+import type { SourceRange } from "@untangle-code/domain";
+export interface LineIndex {
+    readonly buffer: Buffer;
+    /**
+     * Byte offset of the start of each line (0-based), one entry per line,
+     * PLUS one trailing sentinel equal to `buffer.length` — so
+     * `lineStarts[lineCount]` is always a valid "end of file" byte offset.
+     */
+    readonly lineStarts: number[];
+    readonly lineCount: number;
+}
+/** Builds a `LineIndex` from full document content (a decoded UTF-8 string). */
+export declare function buildLineIndex(content: string): LineIndex;
+/**
+ * 1-based line number containing byte offset `byteOffset` (clamped into
+ * `[0, buffer.length]`). Binary search over `lineStarts` (sorted ascending,
+ * one entry per line plus the EOF sentinel — see {@link LineIndex}), used by
+ * any scanner that tracks byte offsets directly (e.g. the SQL adapter's
+ * per-statement spans) and needs the matching 1-based line number without
+ * re-walking the buffer from the start.
+ */
+export declare function lineNumberForByte(index: LineIndex, byteOffset: number): number;
+/**
+ * Builds a `SourceRange` for the 1-based inclusive line span
+ * `[startLine, endLine]`. `endByte` is the byte offset of the start of the
+ * line AFTER `endLine` (or end-of-file for the last line), so two chunks
+ * built from adjacent line spans (`endLine` of one === `startLine - 1` of
+ * the next) are byte-adjacent with no gap and no overlap.
+ */
+export declare function rangeForLines(index: LineIndex, startLine: number, endLine: number): SourceRange;
+/** Decodes the UTF-8 bytes `[startByte, endByte)` as a string. */
+export declare function sliceBytes(index: LineIndex, startByte: number, endByte: number): string;
+/** Convenience: raw content of the 1-based inclusive line span. */
+export declare function sliceLines(index: LineIndex, startLine: number, endLine: number): string;
+/**
+ * Splits content into physical lines WITHOUT their line terminator, plus a
+ * `LineIndex` for range/byte lookups. Adapters that scan line-by-line
+ * (Markdown headings, Dockerfile `FROM`, brace-block scanners, …) use this
+ * once per document.
+ */
+export declare function splitLines(content: string): {
+    lines: string[];
+    index: LineIndex;
+};
+//# sourceMappingURL=line-index.d.ts.map

package/dist/text/line-index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"line-index.d.ts","sourceRoot":"","sources":["../../src/text/line-index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AACH,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEzD,MAAM,WAAW,SAAS;IACxB,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB;;;;OAIG;IACH,QAAQ,CAAC,UAAU,EAAE,MAAM,EAAE,CAAC;IAC9B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;CAC5B;AAED,gFAAgF;AAChF,wBAAgB,cAAc,CAAC,OAAO,EAAE,MAAM,GAAG,SAAS,CAWzD;AAOD;;;;;;;GAOG;AACH,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,SAAS,EAAE,UAAU,EAAE,MAAM,GAAG,MAAM,CAa9E;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,WAAW,CAI/F;AAED,kEAAkE;AAClE,wBAAgB,UAAU,CAAC,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAEvF;AAED,mEAAmE;AACnE,wBAAgB,UAAU,CAAC,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAGvF;AAED;;;;;GAKG;AACH,wBAAgB,UAAU,CAAC,OAAO,EAAE,MAAM,GAAG;IAAE,KAAK,EAAE,MAAM,EAAE,CAAC;IAAC,KAAK,EAAE,SAAS,CAAA;CAAE,CAMjF"}

package/dist/text/line-index.js

@@ -0,0 +1,75 @@
+/** Builds a `LineIndex` from full document content (a decoded UTF-8 string). */
+export function buildLineIndex(content) {
+    const buffer = Buffer.from(content, "utf8");
+    const lineStarts = [0];
+    for (let i = 0; i < buffer.length; i += 1) {
+        if (buffer[i] === 0x0a) {
+            lineStarts.push(i + 1);
+        }
+    }
+    const lineCount = lineStarts.length;
+    lineStarts.push(buffer.length);
+    return { buffer, lineStarts, lineCount };
+}
+function lineStartByte(index, line) {
+    const clamped = Math.min(Math.max(line, 1), index.lineStarts.length);
+    return index.lineStarts[clamped - 1] ?? index.buffer.length;
+}
+/**
+ * 1-based line number containing byte offset `byteOffset` (clamped into
+ * `[0, buffer.length]`). Binary search over `lineStarts` (sorted ascending,
+ * one entry per line plus the EOF sentinel — see {@link LineIndex}), used by
+ * any scanner that tracks byte offsets directly (e.g. the SQL adapter's
+ * per-statement spans) and needs the matching 1-based line number without
+ * re-walking the buffer from the start.
+ */
+export function lineNumberForByte(index, byteOffset) {
+    const target = Math.min(Math.max(byteOffset, 0), index.buffer.length);
+    let low = 0;
+    let high = index.lineCount - 1;
+    while (low < high) {
+        const mid = Math.ceil((low + high) / 2);
+        if ((index.lineStarts[mid] ?? 0) <= target) {
+            low = mid;
+        }
+        else {
+            high = mid - 1;
+        }
+    }
+    return low + 1;
+}
+/**
+ * Builds a `SourceRange` for the 1-based inclusive line span
+ * `[startLine, endLine]`. `endByte` is the byte offset of the start of the
+ * line AFTER `endLine` (or end-of-file for the last line), so two chunks
+ * built from adjacent line spans (`endLine` of one === `startLine - 1` of
+ * the next) are byte-adjacent with no gap and no overlap.
+ */
+export function rangeForLines(index, startLine, endLine) {
+    const startByte = lineStartByte(index, startLine);
+    const endByte = lineStartByte(index, endLine + 1);
+    return { startLine, endLine, startByte, endByte };
+}
+/** Decodes the UTF-8 bytes `[startByte, endByte)` as a string. */
+export function sliceBytes(index, startByte, endByte) {
+    return index.buffer.toString("utf8", startByte, endByte);
+}
+/** Convenience: raw content of the 1-based inclusive line span. */
+export function sliceLines(index, startLine, endLine) {
+    const range = rangeForLines(index, startLine, endLine);
+    return sliceBytes(index, range.startByte, range.endByte);
+}
+/**
+ * Splits content into physical lines WITHOUT their line terminator, plus a
+ * `LineIndex` for range/byte lookups. Adapters that scan line-by-line
+ * (Markdown headings, Dockerfile `FROM`, brace-block scanners, …) use this
+ * once per document.
+ */
+export function splitLines(content) {
+    const index = buildLineIndex(content);
+    // `\r\n` and `\n` both split correctly here; a trailing `\r` (if any) is
+    // stripped so heading/keyword regexes don't have to account for it.
+    const lines = content.split("\n").map((line) => (line.endsWith("\r") ? line.slice(0, -1) : line));
+    return { lines, index };
+}
+//# sourceMappingURL=line-index.js.map

package/dist/text/line-index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"line-index.js","sourceRoot":"","sources":["../../src/text/line-index.ts"],"names":[],"mappings":"AA6BA,gFAAgF;AAChF,MAAM,UAAU,cAAc,CAAC,OAAe;IAC5C,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;IAC5C,MAAM,UAAU,GAAa,CAAC,CAAC,CAAC,CAAC;IACjC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC;QAC1C,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACvB,UAAU,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QACzB,CAAC;IACH,CAAC;IACD,MAAM,SAAS,GAAG,UAAU,CAAC,MAAM,CAAC;IACpC,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;IAC/B,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;AAC3C,CAAC;AAED,SAAS,aAAa,CAAC,KAAgB,EAAE,IAAY;IACnD,MAAM,OAAO,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,KAAK,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC;IACrE,OAAO,KAAK,CAAC,UAAU,CAAC,OAAO,GAAG,CAAC,CAAC,IAAI,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC;AAC9D,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,iBAAiB,CAAC,KAAgB,EAAE,UAAkB;IACpE,MAAM,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,UAAU,EAAE,CAAC,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;IACtE,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,IAAI,IAAI,GAAG,KAAK,CAAC,SAAS,GAAG,CAAC,CAAC;IAC/B,OAAO,GAAG,GAAG,IAAI,EAAE,CAAC;QAClB,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,CAAC,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;QACxC,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,IAAI,MAAM,EAAE,CAAC;YAC3C,GAAG,GAAG,GAAG,CAAC;QACZ,CAAC;aAAM,CAAC;YACN,IAAI,GAAG,GAAG,GAAG,CAAC,CAAC;QACjB,CAAC;IACH,CAAC;IACD,OAAO,GAAG,GAAG,CAAC,CAAC;AACjB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,aAAa,CAAC,KAAgB,EAAE,SAAiB,EAAE,OAAe;IAChF,MAAM,SAAS,GAAG,aAAa,CAAC,KAAK,EAAE,SAAS,CAAC,CAAC;IAClD,MAAM,OAAO,GAAG,aAAa,CAAC,KAAK,EAAE,OAAO,GAAG,CAAC,CAAC,CAAC;IAClD,OAAO,EAAE,SAAS,EAAE,OAAO,EAAE,SAAS,EAAE,OAAO,EAAE,CAAC;AACpD,CAAC;AAED,kEAAkE;AAClE,MAAM,UAAU,UAAU,CAAC,KAAgB,EAAE,SAAiB,EAAE,OAAe;IAC7E,OAAO,KAAK,CAAC,MAAM,CAAC,QAAQ,CAAC,MAAM,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;AAC3D,CAAC;AAED,mEAAmE;AACnE,MAAM,UAAU,UAAU,CAAC,KAAgB,EAAE,SAAiB,EAAE,OAAe;IAC7E,MAAM,KAAK,GAAG,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,OAAO,CAAC,CAAC;IACvD,OAAO,UAAU,CAAC,KAAK,EAAE,KAAK,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC;AAC3D,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,UAAU,CAAC,OAAe;IACxC,MAAM,KAAK,GAAG,cAAc,CAAC,OAAO,CAAC,CAAC;IACtC,yEAAyE;IACzE,oEAAoE;IACpE,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC;IAClG,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC;AAC1B,CAAC"}

package/dist/text/yaml-lite.d.ts

@@ -0,0 +1,73 @@
+/**
+ * Minimal block-style YAML subset parser.
+ *
+ * No YAML/JSON library is added here deliberately (see README
+ * "Entscheidungen"): this package's assigned paths cannot touch the
+ * workspace root lockfile, so pulling in an external dependency mid-wave
+ * would require an edit no other agent could safely race against. Instead
+ * this module implements exactly the YAML subset OpenAPI/AsyncAPI/
+ * Kubernetes/Compose documents actually use in practice: block mappings
+ * and sequences via indentation, single-line flow collections (`{a: 1}`,
+ * `[a, b]`), plain/single/double-quoted scalars, `|`/`>` block scalars,
+ * `#` comments, and `---`/`...` document separators. NOT supported:
+ * anchors/aliases, tags, multi-line flow collections, complex mapping
+ * keys. A document using one of those fails to parse — `parseYamlNode`
+ * throws `YamlParseError`, which every adapter using this module catches
+ * and turns into a visible degrade (architecture.md §22.2: "Parserfehler
+ * degradieren auf Textanalyse"), never a crash.
+ */
+export type YamlScalarValue = string | number | boolean | null;
+export interface YamlScalarNode {
+    kind: "scalar";
+    startLine: number;
+    endLine: number;
+    value: YamlScalarValue;
+}
+export interface YamlMapEntry {
+    key: string;
+    keyLine: number;
+    value: YamlNode;
+}
+export interface YamlMapNode {
+    kind: "map";
+    startLine: number;
+    endLine: number;
+    entries: YamlMapEntry[];
+}
+export interface YamlSeqNode {
+    kind: "seq";
+    startLine: number;
+    endLine: number;
+    items: YamlNode[];
+}
+export type YamlNode = YamlScalarNode | YamlMapNode | YamlSeqNode;
+export declare class YamlParseError extends Error {
+    readonly line: number;
+    constructor(message: string, line: number);
+}
+/** One `---`-separated document within a (possibly multi-document) YAML file. */
+export interface YamlDocumentSpan {
+    startLine: number;
+    endLine: number;
+    text: string;
+}
+/**
+ * Splits raw content into `---`-separated document spans (Kubernetes
+ * manifests, spec.md §19 "je Dokument eine Ressource"). A leading `---` is
+ * just the start of the first document, not an empty document before it. A
+ * trailing `...` end-marker line is treated the same as `---` for the
+ * purpose of ending a document.
+ */
+export declare function splitYamlDocuments(content: string): YamlDocumentSpan[];
+/**
+ * Parses one YAML document's full text (e.g. one `splitYamlDocuments()`
+ * span) into a `YamlNode` tree. Line numbers on every node are 1-based
+ * WITHIN `text` — add `lineOffset` (a span's `startLine - 1`) yourself when
+ * mapping back to the original multi-document file. Returns `null` for a
+ * document that is empty or comments-only. Throws `YamlParseError` (never
+ * any other error type) on anything outside the supported subset.
+ */
+export declare function parseYamlNode(text: string, lineOffset?: number): YamlNode | null;
+export declare function mapGet(node: YamlNode | null | undefined, key: string): YamlNode | undefined;
+export declare function scalarString(node: YamlNode | null | undefined): string | undefined;
+//# sourceMappingURL=yaml-lite.d.ts.map

package/dist/text/yaml-lite.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"yaml-lite.d.ts","sourceRoot":"","sources":["../../src/text/yaml-lite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAEH,MAAM,MAAM,eAAe,GAAG,MAAM,GAAG,MAAM,GAAG,OAAO,GAAG,IAAI,CAAC;AAE/D,MAAM,WAAW,cAAc;IAC7B,IAAI,EAAE,QAAQ,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,eAAe,CAAC;CACxB;AAED,MAAM,WAAW,YAAY;IAC3B,GAAG,EAAE,MAAM,CAAC;IACZ,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,QAAQ,CAAC;CACjB;AAED,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,KAAK,CAAC;IACZ,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,OAAO,EAAE,YAAY,EAAE,CAAC;CACzB;AAED,MAAM,WAAW,WAAW;IAC1B,IAAI,EAAE,KAAK,CAAC;IACZ,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,QAAQ,EAAE,CAAC;CACnB;AAED,MAAM,MAAM,QAAQ,GAAG,cAAc,GAAG,WAAW,GAAG,WAAW,CAAC;AAElE,qBAAa,cAAe,SAAQ,KAAK;aAGrB,IAAI,EAAE,MAAM;gBAD5B,OAAO,EAAE,MAAM,EACC,IAAI,EAAE,MAAM;CAK/B;AAED,iFAAiF;AACjF,MAAM,WAAW,gBAAgB;IAC/B,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,IAAI,EAAE,MAAM,CAAC;CACd;AAED;;;;;;GAMG;AACH,wBAAgB,kBAAkB,CAAC,OAAO,EAAE,MAAM,GAAG,gBAAgB,EAAE,CAkBtE;AAsbD;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAAC,IAAI,EAAE,MAAM,EAAE,UAAU,SAAI,GAAG,QAAQ,GAAG,IAAI,CAY3E;AAID,wBAAgB,MAAM,CAAC,IAAI,EAAE,QAAQ,GAAG,IAAI,GAAG,SAAS,EAAE,GAAG,EAAE,MAAM,GAAG,QAAQ,GAAG,SAAS,CAG3F;AAED,wBAAgB,YAAY,CAAC,IAAI,EAAE,QAAQ,GAAG,IAAI,GAAG,SAAS,GAAG,MAAM,GAAG,SAAS,CAKlF"}